Home Journals Articles Updates About
CN
image
收藏切换
Epicentral distance estimation from a single station based on convolutional neural network
收藏切换
PDF
Shanyou LI1, 2, Yuxuan WANG1, 2, Jindong SONG1, 2, Kunpeng YAO3, Pengjie HUANG3, Jingbao ZHU1, 2
World Earthquake Engineering | 2025, 41(4) : 95 - 105
Less
收藏切换
World Earthquake Engineering | 2025, 41(4): 95-105
Epicentral distance estimation from a single station based on convolutional neural network
Full
Shanyou LI1, 2, Yuxuan WANG1, 2, Jindong SONG1, 2, Kunpeng YAO3, Pengjie HUANG3, Jingbao ZHU1, 2
Affiliations
  • 1.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
  • 2.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China
  • 3.Department of Security Products, Henan Splendor Science & Technology Co., Ltd., Zhengzhou 450012, China
Published: 2025-10-01 doi: 10.19994/j.cnki.WEE.2025.0063
Outline
收藏切换

Estimating the epicentral distance from a single station is a critical task in real-time earthquake early warning systems. To address the limitations of the traditional B-Δ method, which relies on limited P-wave information and exhibits significant prediction errors, this study utilizes strong-motion data from the Japan K-NET network. A 3-second time window of three-component acceleration waveforms is used as input to a convolutional neural network (CNN), which directly extracts feature information from the waveforms to establish a CNN-based epicentral distance estimation model (CNN-Dis). The results show that in the test dataset, by normalizing both the input data and labels, the CNN-Dis model achieves an mean absolute error (MAE) of 28.119 6 km and a standard deviation of 34.682 7 km, outperforming the model without normalization. Compared to the traditional B-Δ method, the CNN-Dis model improves the reliability of epicentral distance estimation. Moreover, the CNN-Dis model provides relatively reliable results for offshore earthquakes, in contrast to inland events. The CNN-Dis model enhances the accuracy of epicentral distance estimation to a certain extent and provides strong support for the iteration and performance optimization of earthquake early warning technologies.

earthquake early warning  /  machine learning  /  convolutional neural network  /  epicentral distance estimation  /  P-wave  /  normalization
Shanyou LI, Yuxuan WANG, Jindong SONG, Kunpeng YAO, Pengjie HUANG, Jingbao ZHU. Epicentral distance estimation from a single station based on convolutional neural network[J]. World Earthquake Engineering, 2025 , 41 (4) : 95 -105 . DOI: 10.19994/j.cnki.WEE.2025.0063
Appendix
Less
Year 2025 volume 41 Issue 4
PDF
56
25
Cite this Article
BibTeX
Article Info
doi: 10.19994/j.cnki.WEE.2025.0063
  • Receive Date：2024-10-08
  • Online Date：2026-03-27
  • Published：2025-10-01
Article Data
Affiliations
History
  • Received：2024-10-08
  • Revised：2025-04-10
Funding
Affiliations
    1.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
    2.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China
    3.Department of Security Products, Henan Splendor Science & Technology Co., Ltd., Zhengzhou 450012, China
References
Share
https://castjournals.cast.org.cn/joweb/sjdzgc/EN/10.19994/j.cnki.WEE.2025.0063
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62199257
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House